产品协同设计中异构模型数据融合的有效策略

薛俊杰; 周军华; 施国强; 宋晓; 蒋炎红; 全红艳

doi:10.13700/j.bh.1001-5965.2020.0699

产品协同设计中异构模型数据融合的有效策略

doi: 10.13700/j.bh.1001-5965.2020.0699

薛俊杰^{1, 2},
周军华^{1, 2, 3},
施国强^{1, 2, 3},
宋晓⁴,
蒋炎红⁵,
全红艳^6, ,

1.
北京仿真中心北京市复杂产品先进制造系统工程技术研究中心，北京 100854
2.
北京电子工程总体研究所复杂产品智能制造系统技术国家重点实验室，北京 100854
3.
北京仿真中心航天系统仿真重点实验室，北京 100854
4.
北京航空航天大学网络空间安全学院，北京 100083
5.
华东师范大学软件工程学院，上海 200062
6.
华东师范大学计算机科学与技术学院，上海 200062

详细信息

通讯作者:
全红艳, E-mail: hyquan@cs.ecnu.edu.cn

中图分类号: V221⁺.3;TB553
计量
- 文章访问数: 455
- HTML全文浏览量: 203
- PDF下载量: 61
- 被引次数: 0
出版历程
- 收稿日期: 2020-12-18
- 录用日期: 2021-04-09
- 网络出版日期: 2022-06-20
- 整期出版日期: 2022-06-20

Effective strategy of heterogeneous model data fusion in product collaborative design

XUE Junjie^{1, 2},
ZHOU Junhua^{1, 2, 3},
SHI Guoqiang^{1, 2, 3},
SONG Xiao⁴,
JIANG Yanhong⁵,
QUAN Hongyan^{6
, ,}

1.
Beijing Complex Product Advanced Manufacturing Engineering Research Center, Beijing Simulation Center, Beijing 100854, China
2.
State Key Laboratory of Intelligent Manufacturing System Technology, Beijing Institute of Electronic System Engineering, Beijing 100854, China
3.
Science and Technology on Space System Simulation Laboratory, Beijing Simulation Center, Beijing 100854, China
4.
School of Cyber Science and Technology, Beihang University, Beijing 100083, China
5.
Software Engineering Institute, East China Normal University, Shanghai 200062, China
6.
School of Computer Science and Technology, East China Normal University, Shanghai 200062, China

More Information

Corresponding author: QUAN Hongyan, E-mail: hyquan@cs.ecnu.edu.cn

摘要

摘要:
针对复杂产品设计中，不同设计工具产生的模型数据之间的融合问题，提出了一种工具间端到端的异构模型数据融合策略。利用数据库管理动态特性，通过模型信息共享，实现异构模型数据之间的融合。在OpenMBEE系统集成环境中，通过建模工具CREO二次开发，利用所提策略获取全生命周期设计中的动态模型属性信息，通过3D模型编辑及重用功能测试，验证了所提策略的有效性。利用自动获取可视化模型属性信息的智能算法，设计一种基于Transformer模型与双向长短期记忆(Bi-LSTM)模型相结合的模型属性智能提取算法，利用神经网络的多层感知特性，通过对模型中属性文本信息进行深度学习、特征分析，实现了对异构数据属性信息的自动提取功能。利用CAMEO建模工具设计的需求分析模型构建模型数据集，验证了智能模型信息自动提取功能的有效性。
- 异构数据 /
- OpenMBEE /
- 数据交换 /
- 多层感知 /
- 深度学习
Abstract:
Aiming at the problem of model data fusion among different design tools in complex product design, the research explores the fusion strategy of end-to-end heterogeneous model data between tools. A multi-layer collaborative strategy of heterogeneous data is proposed, which uses the dynamic characteristics of database management and model attribute sharing to realize the integration of heterogeneous model data. In the system integration environment of OpenMBEE, through the secondary development of the modeling tool CREO, the strategy is employed to obtain the dynamic model attribute information in the whole life cycle design. The effectiveness of the strategy is verified by 3D model editing and reuse function testing. In order to realize the fusion of heterogeneous data, an intelligent algorithm to automatically obtain the attribute information of visual model is explored, based on Transformer model and bi-directional LSTM (Bi-LSTM) model. Utilizing the multi-layer perceptual characteristics of neural network, the algorithm realizes automatic extraction of heterogeneous data attribute information through deep learning and feature analysis of the attribute information in the model. The effectiveness of the intelligent model information extraction is verified by the model data set that is established with the requirement analysis models designed by modeling tool CAMEO.
- heterogeneous data /
- OpenMBEE /
- data exchange /
- multilayer perception /
- deep learning

HTML全文

图 1 集成的组件及工具

Figure 1. Integrated components and tools

下载: 全尺寸图片幻灯片

图 2 多工具集成及协同关系

Figure 2. Multi tool integration and collaborative relationship

下载: 全尺寸图片幻灯片

图 3 建模工具与数据库间协同

Figure 3. Collaboration between modeling tools and databases

下载: 全尺寸图片幻灯片

图 4 分析工具与可视化工具间协同

Figure 4. Collaboration between analysis tools and visualization tools

下载: 全尺寸图片幻灯片

图 5 TF-Net拓扑结构

Figure 5. Topology of TF-Net

下载: 全尺寸图片幻灯片

图 6 网络拓扑结构

Figure 6. Topology of network

下载: 全尺寸图片幻灯片

图 7 Bi-LSTM单元结构

Figure 7. Structure of Bi-LSTM unit

下载: 全尺寸图片幻灯片

图 8 网络的学习和预测过程框架

Figure 8. Framework of network learning and prediction

下载: 全尺寸图片幻灯片

图 9 多层工具协同的验证结果

Figure 9. Validation results of multi-layer tool collaboration

下载: 全尺寸图片幻灯片

图 10 消融实验的性能对比

Figure 10. Performance comparison of ablation experiments

下载: 全尺寸图片幻灯片

参考文献(25)

[1]	GRIEVES M W. Product lift cycle management: The new paradigm for enterprises[J]. International Journal of Product Development, 2005, 2(1-2): 71-84.
[2]	BOSCHERT S, ROSEN R. Digital Twin—The simulation aspect[M]. Berlin: Springer, 2016: 59-74.
[3]	MOUSAVI B A, AZZOUZ R, HEAVEY C, et al. A survey of model-based system engineering methods to analyse complex supply chains: A case study in semiconductor supply chain[J]. IFAC-PaperOnLine, 2019, 52(13): 1254-1259. doi: 10.1016/j.ifacol.2019.11.370
[4]	KRUSE B, BLACKBURN M. Collaborating with OpenMBEE as an authoritative source of truth environment[J]. Procedia Computer Science, 2019, 153: 277-284. doi: 10.1016/j.procs.2019.05.080
[5]	WEILKIENS T. SysML-The systems modeling language[M]//WEILKIENS T. Systems engineering with SysML/UML. Berlin: Springer, 2007: 223-270.
[6]	谢慧敏. 基于XML的数据转换和发布的实现[D]. 南京: 南京理工大学, 2007. XIE H M. Implementation of data transformation and publishing based on XML[D]. Nanjing: Nanjing University of Technology, 2007(in Chinese).
[7]	TAN H, HADZIC F, DILLON T S, et al. Tree model guided candidate generation for mining frequent subtrees from XML documents[J]. ACM Transactions on Knowledge Discovery from Data, 2008, 2(2): 1-43.
[8]	郭丽红, 王箭. 基于PCA的XML文档特征提取方法[J]. 计算机工程与设计, 2011, 32(11): 3894-3896. https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ201111077.htm GUO L H, WANG J. Feature extraction method of XML document based on PCA[J]. Computer Engineering and Design, 2011, 32(11): 3894-3896(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ201111077.htm
[9]	潘有能. XML挖掘: 聚类, 分类与信息提取[M]. 杭州: 浙江大学出版社, 2012. PAN Y N. XML mining: Clustering, classification and information extraction[M]. Hangzhou: Zhejiang University Press, 2012(in Chinese).
[10]	邱实, 袁晓艳, 裴非, 等. 基于配置文件对XML数据进行字段提取及结构化方法: CN109885569A[P]. 2019-06-14. QIU S, YUAN X Y, PEI F, et al. Field extraction and structure method for XML data based on configuration file: CN109885569A[P]. 2019-06-14(in Chinese).
[11]	SONG E, HAW S C. XML-REG: Transforming XML into relational using hybrid-based mapping approach[J]. IEEE Access, 2020, 8: 177623-177639. doi: 10.1109/ACCESS.2020.3026006
[12]	BRAHMIA Z, HAMROUNI H, BOUAZIZ R. XML data manipulation in conventional and temporal XML databases: A survey[J]. Computer Science Review, 2020, 36: 100231. doi: 10.1016/j.cosrev.2020.100231
[13]	MADNI A M, SIEVERS M. Model-based systems engineering: Motivation, current status, and needed advances[M]. Berlin: Springer, 2018: 311-325.
[14]	BONE M, BLACKBURN M, KRUSE B, et al. Toward an interoperability and integration framework to enable digital thread[J]. Systems, 2018, 6(4): 46. doi: 10.3390/systems6040046
[15]	BAYER T J, BENNETT M, DELP C L, et al. Update-concept of operations for integrated model-centric engineering at JPL[C]// 2011 Aerospace Conference. Piscataway: IEEE Press, 2011: 1-15.
[16]	CELLURA M, GUARINO F, LONGO S, et al. Modeling the energy and environmental life cycle of buildings: A co-simulation approach[J]. Renewable and Sustainable Energy Reviews, 2017, 80: 733-742. doi: 10.1016/j.rser.2017.05.273
[17]	GRAIGNIC P, VOSGIEN T, JANKOVIC M, et al. Complex system simulation: Proposition of a MBSE framework for design-analysis integration[J]. Procedia Computer Science, 2013, 16: 59-68. doi: 10.1016/j.procs.2013.01.007
[18]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017: 5998-6008.
[19]	SAHU S K, ANAND A. Drug-drug interaction extraction from biomedical texts using long short-term memory network[J]. Journal of Biomedical Informatics, 2018, 86: 15-24. doi: 10.1016/j.jbi.2018.08.005
[20]	LI F, JIN Y, LIU W, et al. Fine-tuning bidirectional encoder representations from transformers (BERT)-based models on large-scale electronic health record notes: An empirical study[J]. JMIR Medical Informatics, 2019, 7(3): 14830. doi: 10.2196/14830
[21]	GUAN W, SMETANNIKOV I, TIANXING M. Survey on automatic text summarization and transformer models applicability[C]//2020 International Conference on Control, Robotics and Intelligent System, 2020: 176-184.
[22]	ALAPARTHI S, MISHRA M. Bidirectional encoder representations from transformers (BERT): A sentiment analysis odyssey[EB/OL]. (2020-06-02)[2020-12-16]. https://arxiv.org/abs/2007.01127.
[23]	DEVLIN J, CHANG M W, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]// NAACL-HLT 2019, 2019, 1: 4171-4186.
[24]	HUANG Z, XU W, YU K.Bidirectional LSTM-CRF models for sequence tagging[EB/OL]. (2015-08-09)[2020-12-16]. https://arxiv.org/abs/1508.01991.
[25]	李丽双, 郭元凯. 基于CNN-BLSTM-CRF模型的生物医学命名实体识别[J]. 中文信息学报, 2018, 32(1): 116-122. doi: 10.3969/j.issn.1003-0077.2018.01.015 LI L S, GUO Y K. Biomedical named entity recognition based on CNN-BLSTM-CRF model[J]. Chinese Journal of Information, 2018, 32(1): 116-122(in Chinese). doi: 10.3969/j.issn.1003-0077.2018.01.015